scholarly journals Entity Linking Based on Sentence Representation

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Bingjing Jia ◽  
Zhongli Wu ◽  
Pengpeng Zhou ◽  
Bin Wu
Keyword(s):  
Deep Learning ◽  
Knowledge Base ◽  
Attention Mechanism ◽  
Superior Performance ◽  
Learning Approaches ◽  
Entity Linking ◽  
Semantic Meaning ◽  
Representation Model ◽  
Sentence Similarity ◽  
Public Datasets

Entity linking involves mapping ambiguous mentions in documents to the correct entities in a given knowledge base. Most existing methods failed to link when a mention appears multiple times in a document, since the conflict of its contexts in different locations may lead to difficult linking. Sentence representation, which has been studied based on deep learning approaches recently, can be used to resolve the above issue. In this paper, an effective entity linking model is proposed to capture the semantic meaning of the sentences and reduce the noise introduced by different contexts of the same mention in a document. This model first uses the symmetry of the Siamese network to learn the sentence similarity. Then, the attention mechanism is added to improve the interaction between input sentences. To show the effectiveness of our sentence representation model combined with attention mechanism, named ELSR, extensive experiments are conducted on two public datasets. Results illustrate that our model outperforms the baselines and achieves the superior performance.

scholarly journals Deep convolutional neural networks for cardiovascular vulnerable plaque detection

2019 ◽  
Vol 277 ◽  
pp. 02024 ◽  
Author(s):  
Lincan Li ◽  
Tong Jia ◽  
Tianqi Meng ◽  
Yizhe Liu
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Vulnerable Plaque ◽  
Recall Rate ◽  
Superior Performance ◽  
Learning Approaches ◽  
Deep Convolutional Neural Networks ◽  
Vulnerable Plaques ◽  
Plaque Detection

In this paper, an accurate two-stage deep learning method is proposed to detect vulnerable plaques in ultrasonic images of cardiovascular. Firstly, a Fully Convonutional Neural Network (FCN) named U-Net is used to segment the original Intravascular Optical Coherence Tomography (IVOCT) cardiovascular images. We experiment on different threshold values to find the best threshold for removing noise and background in the original images. Secondly, a modified Faster RCNN is adopted to do precise detection. The modified Faster R-CNN utilize six-scale anchors (122,162,322,642,1282,2562) instead of the conventional one scale or three scale approaches. First, we present three problems in cardiovascular vulnerable plaque diagnosis, then we demonstrate how our method solve these problems. The proposed method in this paper apply deep convolutional neural networks to the whole diagnostic procedure. Test results show the Recall rate, Precision rate, IoU (Intersection-over-Union) rate and Total score are 0.94, 0.885, 0.913 and 0.913 respectively, higher than the 1st team of CCCV2017 Cardiovascular OCT Vulnerable Plaque Detection Challenge. AP of the designed Faster RCNN is 83.4%, higher than conventional approaches which use one-scale or three-scale anchors. These results demonstrate the superior performance of our proposed method and the power of deep learning approaches in diagnose cardiovascular vulnerable plaques.

scholarly journals Classification of Hyperspectral Image Based on Double-Branch Dual-Attention Mechanism Network

2020 ◽  
Vol 12 (3) ◽  
pp. 582 ◽  
Author(s):  
Rui Li ◽  
Shunyi Zheng ◽  
Chenxi Duan ◽  
Yang Yang ◽  
Xiqi Wang
Keyword(s):  
Deep Learning ◽  
Hyperspectral Image ◽  
State Of The Art ◽  
Attention Mechanism ◽  
Superior Performance ◽  
Feature Maps ◽  
Spatial Features ◽  
Training Samples ◽  
Series Of Experiments

In recent years, researchers have paid increasing attention on hyperspectral image (HSI) classification using deep learning methods. To improve the accuracy and reduce the training samples, we propose a double-branch dual-attention mechanism network (DBDA) for HSI classification in this paper. Two branches are designed in DBDA to capture plenty of spectral and spatial features contained in HSI. Furthermore, a channel attention block and a spatial attention block are applied to these two branches respectively, which enables DBDA to refine and optimize the extracted feature maps. A series of experiments on four hyperspectral datasets show that the proposed framework has superior performance to the state-of-the-art algorithm, especially when the training samples are signally lacking.

scholarly journals An Encoder-decoder Deep Learning Model Combining Mixed Attention Mechanism and Asymmetric Convolution for Automation of Retinal Vessels Segmentation

2021 ◽  
Author(s):  
Jiajia Cao ◽  
Qin Zhou ◽  
Yi Chen ◽  
Lin Yin ◽  
Fei Zhang
Keyword(s):  
Deep Learning ◽  
Attention Mechanism ◽  
Model Parameters ◽  
Network Architectures ◽  
Retinal Vessels ◽  
Model Combining ◽  
Equal Importance ◽  
Segmentation Methods ◽  
Public Datasets ◽  
Learned Features

The segmentation of the retinal vascular tree is the fundamental step for diagnosing ophthalmological diseases and cardiovascular diseases. Most existing vessel segmentation methods based on deep learning give the learned features equal importance. Ignored the highly imbalanced ratio between background and vessels (the majority of vessel pixels belong to the background), the learned features would be dominantly guided by background, and relatively little influence comes from vessels, often leading to low model sensitivity and prediction accuracy. The reduction of model size is also a challenge. We propose a mixed attention mechanism and asymmetric convolution encoder-decoder structure(MAAC) for segmentation in Retinal Vessels to solve these problems. In MAAC, the mixed attention is designed to emphasize the valid features and suppress the invalid features. It not only identifies information that helps retinal vessels recognition but also locates the position of the vessel. All square convolutions are replaced by asymmetric convolutions because it is more robust to rotational distortions and small convolutions are more suitable for extracting vessel features (based on the thin characteristics of vessels). The employment of asymmetric convolution reduces model parameters and improve the recognition of thin vessel. The experiments on public datasets DRIVE, STARE, and CHASE\_DB1 demonstrated that the proposed MAAC could more accurately segment vessels with a global AUC of 98.17$\%$, 98.67$\%$, and 98.53$\%$, respectively. The mixed attention proposed in this study can be applied to other deep learning models for performance improvement without changing the network architectures. <br>

scholarly journals A study of deep learning approaches for medication and adverse drug event extraction from clinical text

2019 ◽  
Vol 27 (1) ◽  
pp. 13-21 ◽  
Author(s):  
Qiang Wei ◽  
Zongcheng Ji ◽  
Zhiheng Li ◽  
Jingcheng Du ◽  
Jingqi Wang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Learning Algorithms ◽  
Joint Model ◽  
Machine Learning Algorithms ◽  
Entity Recognition ◽  
Superior Performance ◽  
Drug Event ◽  
Support Vector ◽  
Learning Approaches

AbstractObjectiveThis article presents our approaches to extraction of medications and associated adverse drug events (ADEs) from clinical documents, which is the second track of the 2018 National NLP Clinical Challenges (n2c2) shared task.Materials and MethodsThe clinical corpus used in this study was from the MIMIC-III database and the organizers annotated 303 documents for training and 202 for testing. Our system consists of 2 components: a named entity recognition (NER) and a relation classification (RC) component. For each component, we implemented deep learning-based approaches (eg, BI-LSTM-CRF) and compared them with traditional machine learning approaches, namely, conditional random fields for NER and support vector machines for RC, respectively. In addition, we developed a deep learning-based joint model that recognizes ADEs and their relations to medications in 1 step using a sequence labeling approach. To further improve the performance, we also investigated different ensemble approaches to generating optimal performance by combining outputs from multiple approaches.ResultsOur best-performing systems achieved F1 scores of 93.45% for NER, 96.30% for RC, and 89.05% for end-to-end evaluation, which ranked #2, #1, and #1 among all participants, respectively. Additional evaluations show that the deep learning-based approaches did outperform traditional machine learning algorithms in both NER and RC. The joint model that simultaneously recognizes ADEs and their relations to medications also achieved the best performance on RC, indicating its promise for relation extraction.ConclusionIn this study, we developed deep learning approaches for extracting medications and their attributes such as ADEs, and demonstrated its superior performance compared with traditional machine learning algorithms, indicating its uses in broader NER and RC tasks in the medical domain.

scholarly journals A Deep Learning Framework for Malware Classification

2020 ◽  
Vol 12 (1) ◽  
pp. 90-108
Author(s):  
Mahmoud Kalash ◽  
Mrigank Rochan ◽  
Noman Mohammed ◽  
Neil Bruce ◽  
Yang Wang ◽  
...  
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Learning Algorithms ◽  
Superior Performance ◽  
Traditional Learning ◽  
Security Threats ◽  
Learning Approaches ◽  
Learning Framework ◽  
Malware Classification ◽  
New Strategies

In this article, the authors propose a deep learning framework for malware classification. There has been a huge increase in the volume of malware in recent years which poses serious security threats to financial institutions, businesses, and individuals. In order to combat the proliferation of malware, new strategies are essential to quickly identify and classify malware samples. Nowadays, machine learning approaches are becoming popular for malware classification. However, most of these approaches are based on shallow learning algorithms (e.g. SVM). Recently, convolutional neural networks (CNNs), a deep learning approach, have shown superior performance compared to traditional learning algorithms, especially in tasks such as image classification. Inspired by this, the authors propose a CNN-based architecture to classify malware samples. They convert malware binaries to grayscale images and subsequently train a CNN for classification. Experiments on two challenging malware classification datasets, namely Malimg and Microsoft, demonstrate that their method outperforms competing state-of-the-art algorithms.

scholarly journals Deep Learning for COVID-19 Diagnosis from CT Images

2021 ◽  
Vol 11 (17) ◽  
pp. 8227 ◽  
Author(s):  
Andrea Loddo ◽  
Fabio Pili ◽  
Cecilia Di Ruberto
Keyword(s):  
Deep Learning ◽  
Real World ◽  
Heterogeneous Data ◽  
Learning Approaches ◽  
Reference Dataset ◽  
Heterogeneous Data Sources ◽  
Patient Status ◽  
Learning Techniques ◽  
The Cross ◽  
Public Datasets

COVID-19, an infectious coronavirus disease, caused a pandemic with countless deaths. From the outset, clinical institutes have explored computed tomography as an effective and complementary screening tool alongside the reverse transcriptase-polymerase chain reaction. Deep learning techniques have shown promising results in similar medical tasks and, hence, may provide solutions to COVID-19 based on medical images of patients. We aim to contribute to the research in this field by: (i) Comparing different architectures on a public and extended reference dataset to find the most suitable; (ii) Proposing a patient-oriented investigation of the best performing networks; and (iii) Evaluating their robustness in a real-world scenario, represented by cross-dataset experiments. We exploited ten well-known convolutional neural networks on two public datasets. The results show that, on the reference dataset, the most suitable architecture is VGG19, which (i) Achieved 98.87% accuracy in the network comparison; (ii) Obtained 95.91% accuracy on the patient status classification, even though it misclassifies some patients that other networks classify correctly; and (iii) The cross-dataset experiments exhibit the limitations of deep learning approaches in a real-world scenario with 70.15% accuracy, which need further investigation to improve the robustness. Thus, VGG19 architecture showed promising performance in the classification of COVID-19 cases. Nonetheless, this architecture enables extensive improvements based on its modification, or even with preprocessing step in addition to it. Finally, the cross-dataset experiments exposed the critical weakness of classifying images from heterogeneous data sources, compatible with a real-world scenario.

scholarly journals A global land aerosol fine-mode fraction dataset (2001–2020) retrieved from MODIS using hybrid physical and deep learning approaches

2021 ◽  
Author(s):  
Xing Yan ◽  
Zhou Zang ◽  
Zhanqing Li ◽  
Nana Luo ◽  
Chen Zuo ◽  
...  
Keyword(s):  
Deep Learning ◽  
Superior Performance ◽  
Learning Approaches ◽  
Barren Land ◽  
Significance Level ◽  
Global Land ◽  
Fine Mode ◽  
Natural Aerosols ◽  
Land Types

Abstract. The aerosol fine-mode fraction (FMF) is potentially valuable for discriminating natural aerosols from anthropogenic ones. However, most current satellite-based FMF products are highly unreliable. Here, we developed a new satellite-based global land daily FMF dataset (Phy-DL FMF) by synergizing the advantages of physical and deep learning methods at a 1° spatial resolution by covering the period from 2001 to 2020. The Phy-DL FMF dataset is comparable to Aerosol Robotic Network (AERONET) measurements, based on the analysis of 361,089 data samples from 1170 AERONET sites around the world. Overall, Phy-DL FMF showed a root-mean-square error of 0.136 and correlation coefficient of 0.68, and the proportion of results that fell within the ±20 % expected error window was 79.15 %. Phy-DL FMF showed superior performance over alternate deep learning or physical approaches (such as the spectral deconvolution algorithm presented in our previous studies), particularly for forests, grasslands, croplands, and urban and barren land types. As a long-term dataset, Phy-DL FMF is able to show an overall significant decreasing trend (at a 95 % significance level) over global land areas. Based on the trend analysis of Phy-DL FMF for different countries, the upward trend in the FMFs was particularly strong over India and the western USA. Overall, this study provides a new FMF dataset for global land areas that can help improve our understanding of spatiotemporal fine- and coarse-mode aerosol changes. The datasets can be downloaded from https://doi.org/10.5281/zenodo.5105617 (Yan, 2021).

scholarly journals A Survey of Deep Learning-Based Human Activity Recognition in Radar

2019 ◽  
Vol 11 (9) ◽  
pp. 1068 ◽  
Author(s):  
Xinyu Li ◽  
Yuan He ◽  
Xiaojun Jing
Keyword(s):  
Deep Learning ◽  
Activity Recognition ◽  
Human Activity ◽  
Health Assessment ◽  
Human Activity Recognition ◽  
Superior Performance ◽  
Learning Approaches ◽  
The Difference ◽  
High Level ◽  
2D And 3D

Radar, as one of the sensors for human activity recognition (HAR), has unique characteristics such as privacy protection and contactless sensing. Radar-based HAR has been applied in many fields such as human–computer interaction, smart surveillance and health assessment. Conventional machine learning approaches rely on heuristic hand-crafted feature extraction, and their generalization capability is limited. Additionally, extracting features manually is time–consuming and inefficient. Deep learning acts as a hierarchical approach to learn high-level features automatically and has achieved superior performance for HAR. This paper surveys deep learning based HAR in radar from three aspects: deep learning techniques, radar systems, and deep learning for radar-based HAR. Especially, we elaborate deep learning approaches designed for activity recognition in radar according to the dimension of radar returns (i.e., 1D, 2D and 3D echoes). Due to the difference of echo forms, corresponding deep learning approaches are different to fully exploit motion information. Experimental results have demonstrated the feasibility of applying deep learning for radar-based HAR in 1D, 2D and 3D echoes. Finally, we address some current research considerations and future opportunities.

scholarly journals Roundness and positioning deviation prediction in single point incremental forming using deep learning approaches

2019 ◽  
Vol 11 (7) ◽  
pp. 168781401986446
Author(s):  
Sofien Akrichi ◽  
Amira Abbassi ◽  
Sabeur Abid ◽  
Noureddine Ben yahia
Keyword(s):  
Deep Learning ◽  
Incremental Forming ◽  
Single Point ◽  
Deep Belief Network ◽  
Superior Performance ◽  
Single Point Incremental Forming ◽  
Learning Approaches ◽  
Geometric Accuracy ◽  
Forming Process ◽  
Belief Network

This article proposes a deep learning technique for the prevision of the geometric accuracy in single point incremental forming. Moreover, predicting geometric accuracy is one of the most crucial measures of part quality. Accordingly, roundness and positioning deviation are two indicators for measuring geometric accuracy and presenting two output variables. Two types of artificial intelligence learning approaches, that is, shallow learning and deep learning, are investigated and compared for forecasting geometrical accuracy in the single point incremental forming process. Therefore, the back-propagation neural network with one hidden layer is selected as the representative for shallow learning and deep belief network and stack autoencoder are chosen as the representatives for deep learning. Accurate prediction is closely related to the feature learning of single point incremental forming process parameters. The following six parameters were considered as input variables: sheet thickness, tool path direction, step depth, speed rate, feed rate, and wall angle. The results of these studies indicate that deep learning could be a powerful tool in the current search for geometric accuracy prediction in single point incremental forming. Otherwise, the deep learning approach shows the best performance prediction with shallow learning. In addition, the deep belief network model achieves superior performance accuracy for the prediction of roundness and position deviation in comparison with the stack autoencoder approach.

scholarly journals A Broader Look: Camera-Based Vital Sign Estimation across the Spectrum

2019 ◽  
Vol 28 (01) ◽  
pp. 102-114 ◽  
Author(s):  
Christoph Hoog Antink ◽  
Simon Lyra ◽  
Michael Paul ◽  
Xinchi Yu ◽  
Steffen Leonhardt
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Video Compression ◽  
Real World ◽  
Vital Sign ◽  
Healthy Subjects ◽  
Quantitative Information ◽  
Electromagnetic Spectrum ◽  
Learning Approaches ◽  
Public Datasets

Objectives: Camera-based vital sign estimation allows the contactless assessment of important physiological parameters. Seminal contributions were made in the 1930s, 1980s, and 2000s, and the speed of development seems ever increasing. In this suivey, we aim to overview the most recent works in this area, describe their common features as well as shortcomings, and highlight interesting “outliers”. Methods: We performed a comprehensive literature research and quantitative analysis of papers published between 2016 and 2018. Quantitative information about the number of subjects, studies with healthy volunteers vs. pathological conditions, public datasets, laboratory vs. real-world works, types of camera, usage of machine learning, and spectral properties of data was extracted. Moreover, a qualitative analysis of illumination used and recent advantages in terms of algorithmic developments was also performed. Results: Since 2016, 116 papers were published on camera-based vital sign estimation and 59% of papers presented results on 20 or fewer subjects. While the average number of participants increased from 15.7 in 2016 to 22.9 in 2018, the vast majority of papers (n=100) were on healthy subjects. Four public datasets were used in 10 publications. We found 27 papers whose application scenario could be considered a real-world use case, such as monitoring during exercise or driving. These include 16 papers that dealt with non-healthy subjects. The majority of papers (n=61) presented results based on visual, red-green-blue (RGB) information, followed by RGB combined with other parts of the electromagnetic spectrum (n=18), and thermography only (n=12), while other works (n=25) used other mono- or polychromatic non-RGB data. Surprisingly, a minority of publications (n=39) made use of consumer-grade equipment. Lighting conditions were primarily uncontrolled or ambient. While some works focused on specialized aspects such as the removal of vital sign information from video streams to protect privacy or the influence of video compression, most algorithmic developments were related to three areas: region of interest selection, tracking, or extraction of a one-dimensional signal. Seven papers used deep learning techniques, 17 papers used other machine learning approaches, and 92 made no explicit use of machine learning. Conclusion: Although some general trends and frequent shortcomings are obvious, the spectrum of publications related to camera-based vital sign estimation is broad. While many creative solutions and unique approaches exist, the lack of standardization hinders comparability of these techniques and of their performance. We believe that sharing algorithms and/ or datasets will alleviate this and would allow the application of newer techniques such as deep learning.

Sign in / Sign up

Export Citation Format

Share Document